我正在渲染一個 212 行 x 64 列 DF 的整數（final_df），范圍從 0 到 6 作為（無注釋）繪圖注釋熱圖。我正在我的瀏覽器 (microsoft edge) 中使用來自fig.write_html(). 最終的熱圖在我的瀏覽器中呈現得非常緩慢，以至于我收到“頁面無回應”警告，并且任何放大/縮小圖形也非常緩慢。鑒于 df 并不是那么大，這令人驚訝。
誰能建議為什么會這樣以及如何加快速度？
謝謝，蒂姆
def discrete_colorscale(bvals, colors):
#https://chart-studio.plotly.com/~empet/15229/heatmap-with-a-discrete-colorscale/#/
"""
bvals - list of values bounding intervals/ranges of interest
colors - list of rgb or hex colorcodes for values in [bvals[k], bvals[k 1]],0<=k < len(bvals)-1
returns the plotly discrete colorscale
"""
if len(bvals) != len(colors) 1:
raise ValueError('len(boundary values) should be equal to len(colors) 1')
bvals = sorted(bvals)
nvals = [(v-bvals[0])/(bvals[-1]-bvals[0]) for v in bvals] #normalized values
dcolorscale = [] #discrete colorscale
for k in range(len(colors)):
dcolorscale.extend([[nvals[k], colors[k]], [nvals[k 1], colors[k]]])
return dcolorscale
#final_df is a 212 row x 64 col df of ints ranging from 0 to 6
#cell_df is an empty 212x64 df of empty strings to remove cell labelling behaviour
cell_df = final_df.applymap(lambda x: annot_map.get(x, x))
cell_labels = cell_df.values.tolist()
bvals = [0,1,2,3,4,5,6,7]
colors_map = ['rgb(244,244,255)', #whiteish
'rgb(255, 128, 0)', #orange
'rgb(255,0,0)', #red
'rgb(0, 0, 255)', #blue
'rgb(128, 128, 128)', #grey
'rgb(0, 255, 0)', #green
'rgb(192, 192, 192)'] #light grey
dcolorsc = discrete_colorscale(bvals, colors_map)
bvals = np.array(bvals)
tickvals = [np.mean(bvals[k:k 2]) for k in range(len(bvals)-1)]
ticktext = ['param 1',
'param 2',
'param 3',
'param 4',
'param 5',
'param 6',
'param 7']
fig_df = ff.create_annotated_heatmap(final_df.values.tolist(),
x= list(final_df.columns),
y=list(final_df.index),
annotation_text = cell_labels,
colorscale=dcolorsc,
colorbar = dict(thickness=25,
tickvals=tickvals,
ticktext=ticktext),
showscale = True,
zmin=0, zmax=7,
ygap = 1,
xgap = 1,
)
fig_df.update_layout(
xaxis={'title' : 'ID 1'},
yaxis = {'title' : 'ID 2'},
yaxis_nticks = len(final_df.index),
xaxis_nticks = len(final_df.columns)
)
fig_df.write_html(results_file_df)
uj5u.com熱心網友回復：
我懷疑這些注釋對于渲染來說非常昂貴。可能即使您將一個 212x64 的空字串陣列傳遞給annotation_text引數，plotly 仍然必須遍歷它們以確定沒有要添加的注釋。
我創建了一個 212x64 陣列，其中包含 0-6 的隨機整數，并且在我的瀏覽器中呈現也很慢，而且我收到了與您相同的“頁面無回應”警告。
當我使用 時go.heatmap，我能夠獲得看起來與 相同的圖ff.create_annotated_heatmap，這將執行時間從 5-6 秒縮短到 0.66 秒，并且它在瀏覽器中的回應速度也更快。
這似乎比創建帶注釋的熱圖而不使用注釋更直接（是否有特殊原因需要 ff.create_annotated_heatmap 而不是 go.heatmap？）
import numpy as np
import pandas as pd
import plotly.figure_factory as ff
import plotly.graph_objects as go
import time
start_time = time.time()
def discrete_colorscale(bvals, colors):
#https://chart-studio.plotly.com/~empet/15229/heatmap-with-a-discrete-colorscale/#/
"""
bvals - list of values bounding intervals/ranges of interest
colors - list of rgb or hex colorcodes for values in [bvals[k], bvals[k 1]],0<=k < len(bvals)-1
returns the plotly discrete colorscale
"""
if len(bvals) != len(colors) 1:
raise ValueError('len(boundary values) should be equal to len(colors) 1')
bvals = sorted(bvals)
nvals = [(v-bvals[0])/(bvals[-1]-bvals[0]) for v in bvals] #normalized values
dcolorscale = [] #discrete colorscale
for k in range(len(colors)):
dcolorscale.extend([[nvals[k], colors[k]], [nvals[k 1], colors[k]]])
return dcolorscale
#final_df is a 212 row x 64 col df of ints ranging from 0 to 6
#cell_df is an empty 212x64 df of empty strings to remove cell labelling behaviour
## recreate your dfs
np.random.seed(42)
final_df = pd.DataFrame(np.random.randint(0,6,size=(212, 64)), columns=list(range(64)))
# cell_df = final_df.applymap(lambda x: annot_map.get(x, x))
cell_df = pd.DataFrame(np.array(['']*212*64).reshape(212,64), columns=list(range(64)))
cell_labels = cell_df.values.tolist()
bvals = [0,1,2,3,4,5,6,7]
colors_map = ['rgb(244,244,255)', #whiteish
'rgb(255, 128, 0)', #orange
'rgb(255,0,0)', #red
'rgb(0, 0, 255)', #blue
'rgb(128, 128, 128)', #grey
'rgb(0, 255, 0)', #green
'rgb(192, 192, 192)'] #light grey
dcolorsc = discrete_colorscale(bvals, colors_map)
bvals = np.array(bvals)
tickvals = [np.mean(bvals[k:k 2]) for k in range(len(bvals)-1)]
ticktext = ['param 1',
'param 2',
'param 3',
'param 4',
'param 5',
'param 6',
'param 7']
# fig_df = ff.create_annotated_heatmap(final_df.values.tolist(),
# x= list(final_df.columns),
# y=list(final_df.index),
# annotation_text = cell_labels,
# colorscale=dcolorsc,
# colorbar = dict(thickness=25,
# tickvals=tickvals,
# ticktext=ticktext),
# showscale = True,
# zmin=0, zmax=7,
# ygap = 1,
# xgap = 1,
# )
fig_df = go.Figure([go.Heatmap(
z=final_df,
colorscale=dcolorsc,
colorbar=dict(
thickness=25,
tickvals=tickvals,
ticktext=ticktext),
showscale=True,
zmin=0, zmax=7,
ygap=1,
xgap=1,
)
])
fig_df.update_layout(
xaxis={'title' : 'ID 1'},
yaxis = {'title' : 'ID 2'},
yaxis_nticks = len(final_df.index),
xaxis_nticks = len(final_df.columns)
)
fig_df.show()
print(f"Program executed in {time.time() - start_time} seconds")
## original code with figure_factory annotated heatmap: Program executed in 5.351915121078491 seconds
## modified code with graph_objects heatmap: Program executed in 0.6627509593963623 seconds
# fig_df.write_html(results_file_df)
轉載請註明出處，本文鏈接：https://www.uj5u.com/net/394324.html
下一篇：如何從兩個資料表中洗掉重疊序列？